{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:38:31Z","timestamp":1774964311078,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-20-1-0132"],"award-info":[{"award-number":["W911NF-20-1-0132"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Control Netw. Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcns.2024.3401000","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:35:53Z","timestamp":1715708153000},"page":"687-699","source":"Crossref","is-referenced-by-count":9,"title":["Efficient Reward Shaping for Multiagent Systems"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0606-2803","authenticated-orcid":false,"given":"Vrushabh S.","family":"Donge","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3275-9551","authenticated-orcid":false,"given":"Bosen","family":"Lian","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-1615","authenticated-orcid":false,"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2951-442X","authenticated-orcid":false,"given":"Ali","family":"Davoudi","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tac.1978.1101704"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2550866"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.2999304"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.925826"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.12.139"},{"key":"ref6","first-page":"401","article-title":"An actor\/critic algorithm that is equivalent to q-learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Crites","year":"1994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941229"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2970969"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2752845"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref14","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"1999"},{"key":"ref15","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Randlv","year":"1998"},{"key":"ref16","first-page":"565","article-title":"Reward shaping in episodic reinforcement learning","volume-title":"Proc. 16th Conf. Auton. Agents Multiagent Syst.","author":"Grzes","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref18","first-page":"335","article-title":"Inverse optimal control with linearly-solvable MDPs","volume-title":"Proc. 27th Int. Conf. Mach. Learn.","author":"Dvijotham","year":"2010"},{"key":"ref19","first-page":"1","article-title":"Apprenticeship learning via inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abbeel","year":"2004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106635"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2022.3210856"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3114612"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1976.1101342"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3074256"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3058228"},{"issue":"03","key":"ref27","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1142\/S0218127405012429","article-title":"Model reduction for fluids, using balanced proper orthogonal decomposition","volume":"15","author":"Rowley","year":"2005","journal-title":"Int. J. Bifurcation Chaos"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974508"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1017\/S0022112010001217","article-title":"Dynamic mode decomposition of numerical and experimental data","volume":"656","author":"Schmid","year":"2010","journal-title":"J. Fluid Mech."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/15m1013857"},{"issue":"4","key":"ref31","article-title":"Applied koopmanism","volume":"22","author":"Budii","year":"2012","journal-title":"Chaos: Interdiscip. J. Nonlinear Sci."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2023.3259060"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2023.111171","article-title":"Off-policy inverse Q-learning for discrete-time antagonistic unknown systems","volume":"155","author":"Lian","year":"2023","journal-title":"Automatica"},{"key":"ref34","volume-title":"Optimal Control Theory: An Introduction","author":"Kirk","year":"2004"},{"issue":"16","key":"ref35","doi-asserted-by":"crossref","first-page":"5317","DOI":"10.1016\/j.jcp.2012.04.023","article-title":"An improved algorithm for balanced POD through an analytic treatment of impulse response tails","volume":"231","author":"Tu","year":"2012","journal-title":"J. Comput. Phys."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3934\/jcd.2014.1.391"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102568"},{"issue":"11","key":"ref38","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.2514\/2.1570","article-title":"Balanced model reduction via the proper orthogonal decomposition","volume":"40","author":"Willcox","year":"2002","journal-title":"AIAA J."},{"issue":"6","key":"ref39","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1080\/00207178408933239","article-title":"All optimal Hankel-norm approximations of linear multivariable systems and their ${L}^\\infty$-error bounds","volume":"39","author":"Glover","year":"1984","journal-title":"Int. J. Control"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep27300","article-title":"Noise response data reveal novel controllability Gramian for nonlinear network dynamics","volume":"6","author":"Kashima","year":"2016","journal-title":"Sci. Rep."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44851-9_5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5040"}],"container-title":["IEEE Transactions on Control of Network Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6509490\/10935358\/10530345.pdf?arnumber=10530345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:54:38Z","timestamp":1742842478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":42,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcns.2024.3401000","relation":{},"ISSN":["2325-5870","2372-2533"],"issn-type":[{"value":"2325-5870","type":"electronic"},{"value":"2372-2533","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}